© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 236271
    Prev
    Next
    INDEX
    Explanations

    periods and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ết
    0.54
    조
    0.54
     izgled
    0.51
    분
    0.51
    রা
    0.49
    ಬಹು
    0.49
    กล่าว
    0.48
    일
    0.48
    자
    0.47
     więks
    0.47
    POSITIVE LOGITS
    СР
    0.44
    WZ
    0.43
    ondata
    0.43
     For
    0.43
    gun
    0.42
     която
    0.42
    gau
    0.42
     Vene
    0.41
    TIA
    0.40
    URIComponent
    0.40
    Activations Density 0.000%

    No Known Activations